Search Results for author: Dogyoon Song

Found 12 papers, 2 papers with code

Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture

no code implementations CVPR 2024 Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu

This is due to the necessity of tracking extensive forward and reverse diffusion trajectories and employing a large model with numerous parameters across multiple timesteps (i. e. noise levels).

Decoder

Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures

no code implementations14 Dec 2023 Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu

This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i. e., noise levels).

Decoder

Community Detection in High-Dimensional Graph Ensembles

no code implementations6 Dec 2023 Robert Malinas, Dogyoon Song, Alfred O. Hero III

Detecting communities in high-dimensional graphs can be achieved by applying random matrix theory where the adjacency matrix of the graph is modeled by a Stochastic Block Model (SBM).

Community Detection Stochastic Block Model

Algebraic and Statistical Properties of the Ordinary Least Squares Interpolator

1 code implementation27 Sep 2023 Dennis Shen, Dogyoon Song, Peng Ding, Jasjeet S. Sekhon

Deep learning research has uncovered the phenomenon of benign overfitting for overparameterized statistical models, which has drawn significant theoretical interest in recent years.

Causal Inference

Errors-in-variables Fréchet Regression with Low-rank Covariate Approximation

no code implementations16 May 2023 Kyunghee Han, Dogyoon Song

Fr\'echet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables.

regression

Robustness-preserving Lifelong Learning via Dataset Condensation

no code implementations7 Mar 2023 Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu, Alfred Hero

Most work in this learning paradigm has focused on resolving the problem of 'catastrophic forgetting,' which refers to a notorious dilemma between improving model accuracy over new data and retaining accuracy over previous data.

Adversarial Robustness Dataset Condensation +1

Local Minima Structures in Gaussian Mixture Models

no code implementations28 Sep 2020 Yudong Chen, Dogyoon Song, Xumei Xi, Yuqian Zhang

As the objective function is non-convex, there can be multiple local minima that are not globally optimal, even for well-separated mixture models.

valid

Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation

no code implementations NeurIPS 2020 Devavrat Shah, Dogyoon Song, Zhi Xu, Yuzhe Yang

As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold.

Learning Theory reinforcement-learning +1

On Robustness of Principal Component Regression

no code implementations NeurIPS 2019 Anish Agarwal, Devavrat Shah, Dennis Shen, Dogyoon Song

As an important contribution to the Synthetic Control literature, we establish that an (approximate) linear synthetic control exists in the setting of a generalized factor model; traditionally, the existence of a synthetic control needs to be assumed to exist as an axiom.

Art Analysis Causal Inference +3

Learning RUMs: Reducing Mixture to Single Component via PCA

no code implementations31 Dec 2018 Devavrat Shah, Dogyoon Song

Despite the success of RUMs in various domains and the versatility of mixture RUMs to capture the heterogeneity in preferences, there has been only limited progress in learning a mixture of RUMs from partial data such as pairwise comparisons.

Clustering

Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering

no code implementations NeurIPS 2016 Dogyoon Song, Christina E. Lee, Yihua Li, Devavrat Shah

In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings.

Collaborative Filtering Matrix Completion +2

Cannot find the paper you are looking for? You can Submit a new open access paper.